HAIL.SO / DISPATCH · 2026-07-23 · COMPARE
FILE: COMPARE · 6 of 6 slots

side by side.

← all costsclear
01

Large language models

4 models
Alibaba
Qwen3.6-Flash
×
Perplexity
Sonar
×
Alibaba
Qwen3.7-Max
×
OpenAI
GPT-5.3-Codex
×
Output $/MTok$1.50$1.00$7.50$14.00
Input $/MTok$0.25$1.00$2.50$1.75
Cached input $/MTok$0.1750
Context window1,048,576128,0001,048,576400,000
Output cap65,5368,00065,536128,000
Modalitiesin: text, image, video / out: textin: text / out: textin: text / out: textin: text, image / out: text
Tool use
Structured output
FamilyQwen 3.6 FlashSonarQwen 3.7 MaxCodex
Knowledge cutoff2025-08-31
Verified2026-07-192026-07-192026-07-192026-07-19
Sourceprovider page ↗provider page ↗provider page ↗provider page ↗
03

Text to speech

2 models
Rime
Rime Mist v3
×
Deepgram
Deepgram Aura 2
×
$/1M chars$30.00$30.00
Voice qualityneuralneural
Voice cloning
Voice count94
Languagesenen, es, de, fr, nl, it, ja
SSML support
TTFB37ms
Output formatswav, mp3, linear16, mulaw, alaw, opus
Verified2026-07-192026-07-19
Sourceprovider page ↗provider page ↗